Scribd
Upload
116 views43 pages

Experimental Study Design

This document discusses different types of experimental study designs. It begins by explaining the key elements of experimental research, including randomization, manipulation, and the control condition. It then describes different types of experimental designs, from pre-experimental to quasi-experimental to true experimental. Quasi-experimental designs attempt to establish a causal relationship but lack random assignment to conditions. True experimental designs, like randomized controlled trials, use random assignment and aim to establish causality. The document outlines various true experimental designs, including randomized block designs and factorial designs. It concludes by discussing crossover designs and critiques of experimental research methodology.

Uploaded by

proners samratulangi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
116 views43 pages

Experimental Study Design

This document discusses different types of experimental study designs. It begins by explaining the key elements of experimental research, including randomization, manipulation, and the control condition. It then describes different types of experimental designs, from pre-experimental to quasi-experimental to true experimental. Quasi-experimental designs attempt to establish a causal relationship but lack random assignment to conditions. True experimental designs, like randomized controlled trials, use random assignment and aim to establish causality. The document outlines various true experimental designs, including randomized block designs and factorial designs. It concludes by discussing crossover designs and critiques of experimental research methodology.

Uploaded by

proners samratulangi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 43

QUASI-EXPERIMENTAL,

EXPERIMENTAL STUDY DESIGN

Presenter: Nguyen Thi Anh Thu,


Nguyen Van Giang
Instructor: Professor Kuei-Min Chen
CONTENTS
1. Essential elements of experimental research.
- Randomization

- Manipulation

- The control condition

II. Type of Experimental design


- Pre-experimental design

- Quasi-Experimental design.

- True experimental designs

III. Strengths and limitation of experimental designs

2
I. EXPERIMENTAL STUDY DESIGNS

 To provide the greatest amount of control possible to examine


causality more closely.
 To examine cause, one must eliminate all factors influencing
the DV other than the cause (IV) being studied.
 Other factors are eliminated by being controlled.

 Controlled experiments are considered the gold standard


yielding reliable evidence about cause and effect.
 Experimenters can be relatively confident in the authenticity of
causal relationships because they are observed under control
conditions and typically meet the criteria for establishing
causality.

3
4
DESIGN TERMINOLOGY

5
 The three elements of experimental research are (1)
Manipulation, (2) Control, (3) Randomization

(1) Manipulation: The researcher does something to at


least some participants – There are some types of
intervention.

(2) Control: Usually, control group does not receive the


intervention.

(3) Randomization: the researcher assign participants to


a control or experimental condition on a random basis.

6
(1) MANIPULATION
 Experimenters manipulate the IV by administering a treatment
(or intervention) I to some people and withholding it from
others (C), or administering different treatment.
 Experimental deliberately vary the IV ( the presume cause) and
observe the effect from outcome (O).
For example:
Experimental group: R O1 X O2
Control group : R O1 O2
+ Among the question researcher need to address are the
following:
- What is the intervention, and how does it differ from usual
method of care?
- What is specific procedure are to be used with those receiving
7
the intervention?
- What is the dosage or intensity of the intervention?

- Over how long a period with the intervention be administered ,


and how frequently will it be administered, and when will the
treatment begin?

- Who will administer the intervention? What are their


credentials, and what type of training will they receive?

- Under what conditions will the intervention be withdraw or


altered?

- + The most goals of RCTs is to have identical intervention for


all people in the treatment group. 8
(2) THE CONTROL CONDITION
 The term control group refer to a group of participants whose
performance on an outcome is used to evaluate the
performance of treatment group on the same outcome
 The control condition is a proxy for an ideal counterfactual.
 Decision of choosing counterfactual base on theoretical
ground, practical or ethical concern, in some research, control
group no receive treatment.
 Possibilities for the counterfactual include the following:
+ An alternative intervention: Participants receive two different
9
treatment: music versus massage for pain relief.
+ Standard methods of care: that’s , the usual procedure used to
care for patient, the most typical condition in nursing studies.
+ Placebo presumed to have no therapeutic value. Placebo is used
to control for no pharmaceutical effects of drug.
( some patients get drug experiment and others get an innocuous
substances.
+ Different dosage or intensities of treatment: wherein all
participants get some type of intervention: richer, more intense, or
longer. ( dose-response effects).
+ Wait-list control group: with delayed treatment, the control
group eventually receives the full experimental intervention, after
all research outcome are assessed.

10
(3) RANDOMIZATION
 Randomization also called random assignment or random
allocation.

 Involve assigning participant to treatment condition at random.

 Random mean that participants have an equal chance of being


assigned to any group.

 If people are placed in groups randomly, there is no systematic


bias in the groups with respect to pre-intervention attributes that
are potential confounders and could affect outcome.

11
 Randomization procedure:
 The success of randomization depends on two factor:

+ The allocation process should be truly random.


+ There must be strict adherence to the randomization schedule.
- Allocation concealment is intended to prevent biases that could
stem from knowledge of allocation before assignment actually
occur.
- The timing of randomization is also important. Study eligibility -
whether person meets the criteria for inclusion - should be
ascertained before randomization.
- Baseline data should occur before randomization to rule out any
possibility that group assignment might affect baseline
measurement.
12
BLINDING AND MASKING
 A procedure called blinding (or masking) is often used in RCTs
to prevent biases stemming from awareness.
 Blinding involved concealing information from participant,
intervention agent, or data analysts to enhance objectively and
minimize expectation bias.
 When blinding is used with only one group of people ( study
participant), it is sometime describe as a single-blind study.
 When it is possible to mask with two groups ( those delivering
an intervention and those receiving it), it is sometime called
double-blind.
13
4. VARIABLE

14
5. STEP IN CONDUCT EXPERIMENT RESEARCH

15
16
THREAT TO EXTERNAL VALIDITY

17
II. TYPE OF EXPERIMENTAL DESIGNS

18
2.1. PRE-EXPERIMENTAL DESIGN

19
THE ONE-GROUP PRE-POSTTEST DESIGN

20
2.2 QUASI- EXPERIMENTAL DESIGN

21
NONRANDOMIZED GROUP DESIGN

22
23
24
ADVANTAGE OF QUASI-EXPERIMENTAL DESIGN

25
DISADVANTAGE

26
2.3 TRUE EXPERIMENTAL DESIGN
1. Classic Experimental design.

27
28
2. Experimental Posttest-only comparison Group Design.

29
30
Basic experimental (randomization) Designs

31
3. RANDOMIZED BLOCKED DESIGN (RBD)

 RBD uses the two-group pretest-posttest pattern or two-group


posttest pattern with one condition: a blocking variable.

 The blocking variable, if uncontrolled, is expected to


confounding the finding of the study.

 To prevent this confusion, the subject are rank ordered in


relation to the blocking variable.

 This process ensure that the experimental group and the


control group are equal in relation to the potentially
confounding variable. 32
FOR EXAMPLE: GENDER IS CONFOUNDING VARIABLE, WE BLOCK
GENDER.

33
4 FACTORIAL DESIGN
 Two or more different characteristics, treatment, or event are
independently varied within a single study.
 This design is a logical approach to examining multi-causality.

 The simplest arrangement refer to 2 * 2 factors: there are two


treatment or factors, within each factor, two levels are
manipulated.
 Extension of the factorial design to more that two levels of
variance are to refer to as N * M factorial design.
For example: 3 * 3 or 4 * 4.
 Factorial design are not limited to two independent variable:
however, interpretation of large numbers becomes more
complex and required greater knowledge of statistical analysis.

34
Control
group

35
36
5. CROSSOVER OR COUNTERBALANCED DESIGN

 In some studies: More than one treatment is administered to each


subject. The treatment are provided sequentially rather than
concurrently.
 Comparison are then made of the effect of the different treatments
on the same subject. The direct interaction of one treatment with
another can confound differences in the two treatment.
 Crossover is a strategy designed to guard against possible
erroneous conclusion resulting from carryover effect.
 The design must allow for an adequate interval between treatment
to dissipate the effect of the first treatment. The interval refer to as
a washout period.
37
Crossover design

38
CROSSOVER DESIGN

39
40
CRITIQUE FOR EXPERIMENTAL RESEARCH

41
CRITIQUE (CON’T)

42
Thank you very much

43

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy